Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1320328 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 430143 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1600548 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2364. Min Act: -0.0000

Data Index: 904232 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2475. Min Act: -0.0000

Data Index: 636652 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1077478 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1599919 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2353. Min Act: -0.0000

Data Index: 564619 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2181. Min Act: -0.0000

Data Index: 466292 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2251. Min Act: -0.0000

Data Index: 107012 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1297855 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1475483 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1414742 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1316141 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1632057 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1155637 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1548435 (Python Code)

Max Activating Token Index: 433

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2182. Min Act: -0.0000

Data Index: 28339 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2089. Min Act: -0.0000

Data Index: 580740 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1486396 (Python Code)

Max Activating Token Index: 943